© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23547
    Prev
    Next
    INDEX
    Explanations

    terms related to responses or replies in a communication context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    مصادر
    -0.85
     OAS
    -0.82
    thest
    -0.81
     Moseley
    -0.79
    ölkerung
    -0.77
     عشر
    -0.75
    jsxFileName
    -0.75
     Moos
    -0.74
     HTMLElement
    -0.73
    aced
    -0.73
    POSITIVE LOGITS
    replies
    0.96
    Reply
    0.95
    reply
    0.90
     Reply
    0.88
     replies
    0.84
     reply
    0.84
    Replies
    0.82
     REPLY
    0.81
     Replies
    0.80
    REPLY
    0.77
    Activations Density 0.006%

    No Known Activations